SOTAVerified

Imitation Learning

Imitation Learning is a framework for learning a behavior policy from demonstrations. Usually, demonstrations are presented in the form of state-action trajectories, with each pair indicating the action to take at the state being visited. In order to learn the behavior policy, the demonstrated actions are usually utilized in two ways. The first, known as Behavior Cloning (BC), treats the action as the target label for each state, and then learns a generalized mapping from states to actions in a supervised manner. Another way, known as Inverse Reinforcement Learning (IRL), views the demonstrated actions as a sequence of decisions, and aims at finding a reward/cost function under which the demonstrated decisions are optimal.

Finally, a newer methodology, Inverse Q-Learning aims at directly learning Q-functions from expert data, implicitly representing rewards, under which the optimal policy can be given as a Boltzmann distribution similar to soft Q-learning

Source: Learning to Imitate

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1151–1160 of 2122 papers

TitleStatusHype
Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning—0
Self-Imitation Learning from Demonstrations—0
Teachable Reinforcement Learning via Advice DistillationCode1
Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation—0
An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models—0
MotionAug: Augmentation with Physical Correction for Human Motion PredictionCode1
Causal Robot Communication Inspired by Observational Learning Insights—0
Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging taskCode0
Policy Architectures for Compositional Generalization in Control—0
Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations—0
Show:102550
← PrevPage 116 of 213Next →

No leaderboard results yet.